How to Use the Obsidian Publish MCP in Google ADK

Q: How do I integrate Obsidian Publish with Google ADK?

Install the toolset using the McpToolset class. Provide your server parameters, and pass the object to your LlmAgent instance.

Q: Can Google ADK filter the Obsidian Publish tools?

You can use the toolnames filter in your McpToolset configuration. This restricts the agent to only the tools you explicitly permit.

Q: What happens if my Obsidian Publish site structure changes?

The agent will detect the change during its next listfiles or listnavigation call. It dynamically updates its knowledge of your site's topology.

Link your Google ADK agents to Obsidian Publish to reason over your private knowledge base.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Obsidian Publish MCP to Google ADK

Create your Vinkius account to connect Obsidian Publish to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Obsidian Publish with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deep knowledge crawling for Google ADK

Your agent uses `list_navigation` to traverse your vault's hierarchy. It builds an internal graph of your knowledge before performing any deep-dive queries. This method is faster than manual searching. It allows your agent to find related notes by following your existing folder structure and link mappings.

Contextual metadata extraction

The agent uses `get_metadata` to filter notes by creation hashes and frontmatter properties. This allows it to ignore irrelevant files and focus on core content. It then retrieves specific markdown content via `get_file`. This targeted approach keeps your Gemini long-context window optimized for relevant information only.

Enterprise-ready site discovery

Your agent calls `site_info` to map global site settings. It understands your site's layout, ensuring it interprets your markdown files with the correct context. This integration is designed for production environments. It works alongside your existing Google Cloud infrastructure to provide accurate answers from your notes.

Setup guide

Set up Obsidian Publish MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Obsidian Publish tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Obsidian Publish_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Obsidian Publish tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Obsidian Publish. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Obsidian Publish now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Obsidian Publish MCP in Google ADK

Install the toolset using the `McpToolset` class. Provide your server parameters, and pass the object to your `LlmAgent` instance.

You can use the `tool_names` filter in your `McpToolset` configuration. This restricts the agent to only the tools you explicitly permit.

It supports both transport methods. Most users choose HTTP for better scalability when running agents on Google Cloud infrastructure.

The agent will detect the change during its next `list_files` or `list_navigation` call. It dynamically updates its knowledge of your site's topology.

Data is transmitted through an encrypted tunnel. The server only accesses your markdown files and associated site metadata, keeping your private knowledge isolated.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript